Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections of academic writing related to methodology and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Section headers followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    technical document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somewhere
    -0.50
     someplace
    -0.47
    yorlar
    -0.45
    قایناقلار
    -0.43
     zucchero
    -0.42
    ziehungs
    -0.42
     something
    -0.41
     him
    -0.41
     eit
    -0.41
     noqa
    -0.40
    POSITIVE LOGITS
     utafitiHapana
    0.76
     مشين
    0.75
    UIControlState
    0.70
    fread
    0.68
    RectangleBorder
    0.68
    ंदीखरीदारी
    0.67
    enderror
    0.64
     onAnimation
    0.64
    interopRequire
    0.64
     дописавши
    0.63
    Act Density 0.129%

    No Known Activations